Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 14419
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal arguments and claims of evidence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    followed by "that"

    np_acts-logits-general · gemini-2.0-flash

    opinion followed by that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quels
    -0.67
    PYX
    -0.50
    autique
    -0.49
    ]').
    -0.49
    UTION
    -0.47
     ویکی‌پدیای
    -0.47
    ValueStyle
    -0.47
    "?>
    -0.46
    ----</
    -0.46
    ]?
    -0.45
    POSITIVE LOGITS
     that
    2.42
     bahwa
    1.91
     rằng
    1.65
     ότι
    1.54
     bahawa
    1.51
    ว่า
    1.38
     kwamba
    1.38
     że
    1.33
    that
    1.30
     πως
    1.24
    Activations Density 1.386%

    No Known Activations